Invited talk by Dr. Muhammad Rizwan Asif

Title of the talk: Machine learning opportunities for geoscientific investigations

Info about event

Time

Tuesday 25 April 2023,  at 13:00 - 14:00

Location

Finlandsgade 20, 5124-038

Abstract:

Machine learning, especially deep learning methods, have shown incredible potential in many application areas including image and speech recognition, natural language processing, robotics, fraud detection and medical diagnosis. However, the adoption of deep learning algorithms for geoscientific investigations has been rather slow and hindered by lack of generalization capabilities and benchmarking datasets. Significant gains can be produced by integrating deep learning paradigms in geoscientific workflows by improving data processing, analysis, and decision-making, leading to efficient and effective resource management and environmental protection. In this talk, I will discuss my recent deep learning developments for improving the geoscientific data processing workflows and provide some insights into how generalizable methods can be developed. As the technology continues to advance, it is expected to have an even greater impact on geoscientific investigations.

 

Bio:

Dr. Muhammad Rizwan Asif received his BSc. degree in electrical (telecommunication) engineering from COMSATS University Islamabad (CUI) in 2013, and the MSc. and Ph.D. in information and communication engineering from Xi’an Jiaotong University in 2016 and 2019 respectively. From September 2019 to August 2020. he worked as a postdoc with the Department of Engineering at Aarhus University, Denmark. He is working in close collaboration with the Hydrogeophysics Group (HGG) at the Department of Geoscience, Aarhus University, to support research projects employing electrical and electromagnetic methods. Since September 2020, he has been working as a postdoc in HGG, Department of Geoscience, Aarhus University. His current research interests include machine learning applications for geophysical data. He is also interested in image processing and computer vision for intelligent automated systems.